MCP server · trust report

io.github.AgentsKit-io/doc-bridge

1 check that ran failed — version behavior — so this release can’t be trusted as-is.

Publisher
io.github.AgentsKit-io
Repository
github.com/AgentsKit-io/doc-bridge
Install
npm:@agentskit/doc-bridge, npm:@agentskit/doc-bridge
Versions
2
Inspected
4 of 6 checks · 65%
Scored
2026-09-04 · rubric 1.0.0

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

6 checks1 clean3 flagged2 not inspected
  • Injection surface

    unscannable25% of grade

    Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

    No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.

  • Supply chain

    warn25% of grade

    Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

    install hook "prepare" present and not a recognized benign build command

  • Credential hygiene

    pass15% of grade

    How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

    Reads secrets from the environment (e.g. src/intelligence/adapter.ts) — the recommended intake shape. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

  • Permission scope

    warn15% of grade

    Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

    references credential paths: src/cli/demo.ts: references a credential path (/mcp.json) has both shell/exec and network egress — capable of download-and-run, though no such path was observed (scripts/prepare.mjs: imports child_process and calls exec/spawn; scripts/check-ecosystem-upstream.mjs: outbound HTTP/socket call). discloses shell/exec capability: scripts/prepare.mjs: imports child_process and calls exec/spawn discloses shell/exec capability: examples/verify-handoff.mjs: imports child_process and calls exec/spawn discloses shell/exec capability: src/memory/github-pr.ts: imports child_process and calls exec/spawn Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

  • Version behavior

    fail10% of grade

    Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

    vs prior 1.2.4 (patch bump): new capability primitive(s) in source: child_process, http-client; new hardcoded outbound host/BCC destination(s): 127.0.0.1, agentskit.io, doc-bridge.agentskit.io, github.com, img.shields.io, json-schema.org, playbook.agentskit.io, raw.githubusercontent.com, www.npmjs.com.

  • Transport config

    unscannable10% of grade

    Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

    local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.

Version history

Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.

VersionPublishedGradeScoreInspectedChange
v1.2.6 · current2026-08-03 C704/6 · 65%B→C in v1.2.6
v1.2.42026-07-22 B87.53/6 · 55%